Fast Neural Network Inference on FPGAs for Triggering on Long-Lived Particles at Colliders

TL;DR

This paper explores the use of FPGA-accelerated machine learning algorithms for real-time event selection in particle physics, demonstrating their efficiency and suitability for high-luminosity collider triggers.

Contribution

It introduces two FPGA-accelerated machine learning algorithms optimized for detecting long-lived particles, showing their accuracy and low latency in a collider trigger context.

Findings

Algorithms meet latency requirements for second-level triggers

FPGA acceleration maintains accuracy of models

Hardware setups outperform CPU and GPU in inference time

Abstract

Experimental particle physics demands a sophisticated trigger and acquisition system capable to efficiently retain the collisions of interest for further investigation. Heterogeneous computing with the employment of FPGA cards may emerge as a trending technology for the triggering strategy of the upcoming high-luminosity program of the Large Hadron Collider at CERN. In this context, we present two machine-learning algorithms for selecting events where neutral long-lived particles decay within the detector volume studying their accuracy and inference time when accelerated on commercially available Xilinx FPGA accelerator cards. The inference time is also confronted with a CPU- and GPU-based hardware setup. The proposed new algorithms are proven efficient for the considered benchmark physics scenario and their accuracy is found to not degrade when accelerated on the FPGA cards. The results indicate that all tested architectures fit within the latency requirements of a second-level trigger farm and that exploiting accelerator technologies for real-time processing of particle-physics collisions is a promising research field that deserves additional investigations, in particular with machine-learning models with a large number of trainable parameters.